A method is provided for a content recommendation module. The method includes receiving a user input related to viewing contents from a user and determining whether a recommendation pool containing a plurality of selected recommendation candidates has been changed corresponding to the input. The method also includes, when the recommendation pool has been changed, mapping the plurality of selected recommendation candidates in the changed recommendation pool into a hierarchical data structure with a plurality of levels such that each of the plurality of levels acts as a stage of a zoom operation on the selected recommendation candidates. Further, the method includes rendering mapped recommendation candidates from the plurality of levels to be displayed to the user.
Legal claims defining the scope of protection, as filed with the USPTO.
1. A method for a content recommendation module, comprising: receiving a user input related to viewing contents from a user; determining that a recommendation pool containing a plurality of selected recommendation candidates has been changed corresponding to the input; when the recommendation pool has been changed, mapping the plurality of selected recommendation candidates in the changed recommendation pool into a hierarchical data structure with a plurality of levels such that each of the plurality of levels acts as a stage of a zoom operation on the selected recommendation candidates, wherein the hierarchical data structure has a center point being a most representative recommendation, and recommendation candidates at each of the plurality of levels are related in content to the center point and rendered around the center point; and rendering mapped recommendation candidates from the plurality of levels to be displayed to the user, wherein mapping the plurality of selected recommendation candidates further includes: dividing a space of each of the plurality of levels into sub-spaces; mapping the recommendation candidates into the divided sub-spaces; and when each sub-space at a same level does not contain the same number of recommendation candidates, moving extra recommendation candidates from a certain sub-space of the same level to one or more sub-spaces of the same level with less recommendation candidates.
2. The method according to claim 1 , wherein: the plurality of selected recommendation candidates are selected based on at least a user behavior pattern.
3. The method according to claim 2 , wherein: the user behavior pattern is a remote control key transferring pattern represented by probabilities of remote control key node transitions, wherein a remote control key node includes one or more similar remote control keys.
4. The method according to claim 3 , wherein: provided that Pu(Ki) denotes a probability of using remote control key node Ki, and Pu(KiKj) denotes a probability of transition from remote control key node Ki to remote control key node Kj, where i and j are indices of the remote control key nodes, u is an index of the user, Pu(Ki) is calculated as a total using frequency of remote control key node Ki divided by a total using frequency of all remote control key nodes.
5. The method according to claim 1 , wherein: the plurality of selected recommendation candidates are selected based on at least a user preference determined based on a viewing history of the user.
6. The method according to claim 1 , further including: selecting the recommendation candidates based on mood of the user, preference of the user, and recommendations for other users.
7. The method according to claim 6 , further including: selecting the recommendation candidates using a content database with all titles, a database storing titles that were recently selected by other users in substantial similar interest groups as the user, and a database storing content that the user viewed in a recent time period.
8. The method according to claim 1 , wherein: the hierarchical data structure is a pyramid hierarchical data structure with a plurality of levels and, provided that n is a level number, a total number of the recommendation candidates at each of the plurality of levels is determined as 2 n ×2 n =2 2n ; and a top level is displayed by a single icon as an indication for zoomable recommendation operation.
9. The method according to claim 1 , further including: setting an initial recommendation level around middle of the plurality of levels, such that the user starts by accessing a mid-level of the hierarchical data structure.
10. The method according to claim 1 , further including: reducing dimensions of the recommendation candidates to a 2D dimension.
11. The method according to claim 1 , wherein mapping the plurality of selected recommendation candidates further includes: a. setting a current recommendation level to level 0 and a current space of the level 0; b. determining that the current recommendation level is not greater than a predetermined value; c. increasing the current recommendation level by a step value d. dividing the current space into a plurality of equal-sized sub-spaces; e. mapping the recommendation candidates into the divided sub-spaces such that each sub-space contains same number of recommendation candidates; and f. repeating steps be until the current recommendation level is greater than the predetermined value.
12. The method according to claim 11 , further including: when a sub-space is mapped into more than one recommendation candidates, determining a representative content to represent the more than one recommendation candidates to represent the sub-space when displaying the recommendation to the user.
13. A content recommendation module, comprising: a database configured to store a recommendation pool containing a plurality of selected recommendation candidates; a user interaction handler configured to receive a user input related to viewing contents from a user and to determine that the recommendation pool has been changed corresponding to the input; a content remapping unit configured to, when the recommendation pool has been changed, map the plurality of selected recommendation candidates in the changed recommendation pool into a hierarchical data structure with a plurality of levels such that each of the plurality of levels acts as a stage of a zoom operation on the selected recommendation candidates, wherein the hierarchical data structure has a center point being a most representative recommendation, and recommendation candidates at each of the plurality of levels are related in content to the center point and rendered around the center point; and a rendering engine configured to render mapped recommendation candidates from the plurality of levels to be displayed to the user, wherein, to map the plurality of selected recommendation candidates, the content remapping unit is further configured to: divide a space of each of the plurality of levels into sub-spaces; map the recommendation candidates into the divided sub-spaces; and when each sub-space at a same level does not contain the same number of recommendation candidates, move extra recommendation candidates from a certain sub-space of the same level to one or more sub-spaces of the same level with less recommendation candidates.
14. The content recommendation module according to claim 13 , wherein: the plurality of selected recommendation candidates are selected based on at least a user behavior pattern.
15. The content recommendation module according to claim 14 , wherein: the user behavior pattern is a remote control key transferring pattern represented by probabilities of remote control key node transitions, wherein a remote control key node includes one or more similar remote control keys.
16. The content recommendation module according to claim 15 , wherein: provided that Pu(Ki) denotes a probability of using remote control key node Ki, and Pu(KiKj) denotes a probability of transition from remote control key node Ki to remote control key node Kj, where i and j are indices of the remote control key nodes, u is an index of the user, Pu(Ki) is calculated as a total using frequency of remote control key node Ki divided by a total using frequency of all remote control key nodes.
17. The content recommendation module according to claim 13 , wherein: the plurality of selected recommendation candidates are selected based on at least a user preference determined based on a viewing history of the user.
18. The content recommendation module according to claim 13 , further including: selecting the recommendation candidates based on mood of the user, preference of the user, and recommendations for other users.
19. The content recommendation module according to claim 18 , further including: an analytic engine configured to select the recommendation candidates using a content database with all titles, a database storing titles that were recently selected by other users in substantial similar interest groups as the user, and a database storing content that the user viewed in a recent time period.
20. The content recommendation module according to claim 13 , wherein: the hierarchical data structure is a pyramid hierarchical data structure with a plurality of levels and, provided that n is a level number, a total number of the recommendation candidates at each of the plurality of levels is determined as 2 n ×2 n =2 2n ; and a top level is displayed by a single icon as an indication for zoomable recommendation operation.
21. The content recommendation module according to claim 13 , wherein the content remapping unit is further configured to: a. set a current recommendation level to level 0 and a current space of the level 0; b. determine that the current recommendation level is not greater than a predetermined value; c. increase the current recommendation level by a step value d. divide the current space into a plurality of equal-sized sub-spaces; e. map the recommendation candidates into the divided sub-spaces such that each sub-space contains same number of recommendation candidates; and f. repeat steps b-e until the current recommendation level is greater than the predetermined value.
22. The content recommendation module according to claim 21 , wherein the content remapping unit is further configured to: when a sub-space is mapped into more than one recommendation candidates, determine a representative content to represent the more than one recommendation candidates to represent the sub-space when displaying the recommendation to the user.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
October 30, 2012
October 21, 2014
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.